gemini-interactions-api — Skills

What it does

gemini-3.6-flash: 1M tokens, fast, balanced performance for agentic and multimodal tasks

gemini-3.5-flash-lite: 1M tokens, fastest, lowest-cost 3.5 model for high-throughput execution

gemini-3.1-pro-preview: 1M tokens, complex reasoning, coding, research

gemini-3.1-flash-lite: cost-efficient, fastest performance for high-frequency, lightweight tasks

gemini-3-pro-image (Nano Banana Pro): 65k / 32k tokens, high-quality image generation and editing

gemini-3.1-flash-image (Nano Banana 2): 65k / 32k tokens, fast, efficient image generation and editing

gemini-3.1-flash-lite-image (Nano Banana 2 Lite): 65k / 32k tokens, ultra-fast image generation and editing

Requirements & configuration

Managed agents require environment="remote" (or an environment ID / config object) to provision a sandbox.

Use deep-research-preview-04-2026 for fast research or deep-research-max-preview-04-2026 for maximum exhaustiveness. Agents require background=True.

| text | modeloutput | Incremental text token. |

gemini interactions api

Source

Repository: https://github.com/google-gemini/gemini-skills

gemini-interactions-api FAQ

What does the gemini-interactions-api skill do?

Use this skill when writing code that calls the Gemini API for text generation, multi-turn chat, multimodal understanding, image generation, video generation, streaming responses, background research tasks, function calling, structured output, or migrating from the old generateContent API. This skill covers the Interactions API, the recommended way to use Gemini models and agents in Python and TypeScript. gemini-3.6-flash: 1M tokens, fast, balanced performance for agentic and multimodal tasks gemini-3.5-flash-lite: 1M tokens, fastest, lowest-cost 3.5 model for high-throughput execution

What does gemini-interactions-api require?

Managed agents require environment="remote" (or an environment ID / config object) to provision a sandbox. Use deep-research-preview-04-2026 for fast research or deep-research-max-preview-04-2026 for maximum exhaustiveness. Agents require background=True. | text | modeloutput | Incremental text token. |

How do I install gemini-interactions-api?

Run: npx -y skills add https://github.com/google-gemini/gemini-skills --skill gemini-interactions-api --agent claude-code — the source lives at github.com/google-gemini/gemini-skills.

Maintain gemini-interactions-api?

Let people know it's listed here — add the badge (live metrics, light/dark aware) or a plain link to your README or docs.

[![gemini-interactions-api on getagentictools](https://getagentictools.com/badge/skills/google-gemini-gemini-skills-gemini-interactions-api.svg)](https://getagentictools.com/skills/google-gemini-gemini-skills-gemini-interactions-api?ref=badge)

npx agentictools info skills/google-gemini-gemini-skills-gemini-interactions-api

The second line is the CLI lookup for this page — handy in READMEs and docs.